developer_uid: NischayDnk
submission_id: chaiml-mistral-fulldata_16288_v1
model_name: chaiml-mistral-fulldata_16288_v1
model_group: ChaiML/mistral-fulldatas
status: torndown
timestamp: 2025-04-30T04:25:33+00:00
num_battles: 7990
num_wins: 4626
celo_rating: 1327.77
family_friendly_score: 0.5406
family_friendly_standard_error: 0.007047717928521259
submission_type: basic
model_repo: ChaiML/mistral-fulldatasimpo-24b-retrysft-v2
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5616091675470392, 'latency_mean': 1.780529259443283, 'latency_p50': 1.7850254774093628, 'latency_p90': 1.9838815927505493}, {'batch_size': 3, 'throughput': 1.171582449134001, 'latency_mean': 2.555240226984024, 'latency_p50': 2.5866737365722656, 'latency_p90': 2.8305654287338258}, {'batch_size': 5, 'throughput': 1.535936663236791, 'latency_mean': 3.2414451575279237, 'latency_p50': 3.245894193649292, 'latency_p90': 3.5906389951705933}, {'batch_size': 6, 'throughput': 1.6809291321606976, 'latency_mean': 3.5492157626152037, 'latency_p50': 3.511663317680359, 'latency_p90': 4.027025842666626}, {'batch_size': 8, 'throughput': 1.8567451745422245, 'latency_mean': 4.259580609798431, 'latency_p50': 4.250660181045532, 'latency_p90': 4.866168093681336}, {'batch_size': 10, 'throughput': 1.9610634755310434, 'latency_mean': 5.045007019042969, 'latency_p50': 5.0604753494262695, 'latency_p90': 5.592336201667786}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-mistral-fulldata_16288_v1
is_internal_developer: False
language_model: ChaiML/mistral-fulldatasimpo-24b-retrysft-v2
model_size: 24B
ranking_group: single
throughput_3p7s: 1.74
us_pacific_date: 2025-04-29
win_ratio: 0.5789737171464331
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_start|>', '\n', '<|im_end|>'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', 'truncate_by_message': False}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-mistral-fulldata-16288-v1-mkmlizer
Waiting for job on chaiml-mistral-fulldata-16288-v1-mkmlizer to finish
chaiml-mistral-fulldata-16288-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-fulldata-16288-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-fulldata-16288-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-fulldata-16288-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-fulldata-16288-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-fulldata-16288-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-fulldata-16288-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-fulldata-16288-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-mistral-fulldata-16288-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-fulldata-16288-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-fulldata-16288-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-fulldata-16288-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-fulldata-16288-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-fulldata-16288-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-fulldata-16288-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-fulldata-16288-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-fulldata-16288-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral-fulldata-16288-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-fulldata-16288-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-fulldata-16288-v1-mkmlizer: Downloaded to shared memory in 79.495s
chaiml-mistral-fulldata-16288-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpul1a2fv6, device:0
chaiml-mistral-fulldata-16288-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-fulldata-16288-v1-mkmlizer: quantized model in 54.100s
chaiml-mistral-fulldata-16288-v1-mkmlizer: Processed model ChaiML/mistral-fulldatasimpo-24b-retrysft-v2 in 133.595s
chaiml-mistral-fulldata-16288-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-fulldata-16288-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-fulldata-16288-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-fulldata-16288-v1
chaiml-mistral-fulldata-16288-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-fulldata-16288-v1/config.json
chaiml-mistral-fulldata-16288-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-fulldata-16288-v1/special_tokens_map.json
chaiml-mistral-fulldata-16288-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-fulldata-16288-v1/tokenizer_config.json
chaiml-mistral-fulldata-16288-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-fulldata-16288-v1/tokenizer.json
chaiml-mistral-fulldata-16288-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral-fulldata-16288-v1/flywheel_model.1.safetensors
chaiml-mistral-fulldata-16288-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-fulldata-16288-v1/flywheel_model.0.safetensors
Job chaiml-mistral-fulldata-16288-v1-mkmlizer completed after 165.57s with status: succeeded
Stopping job with name chaiml-mistral-fulldata-16288-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.09s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-fulldata-16288-v1
Waiting for inference service chaiml-mistral-fulldata-16288-v1 to be ready
Inference service chaiml-mistral-fulldata-16288-v1 ready after 140.59260082244873s
Pipeline stage MKMLDeployer completed in 141.01s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.626525402069092s
Received healthy response to inference request in 1.8958420753479004s
Received healthy response to inference request in 1.9201924800872803s
Received healthy response to inference request in 2.1956939697265625s
5 requests
1 failed requests
5th percentile: 1.9007121562957763
10th percentile: 1.9055822372436524
20th percentile: 1.9153223991394044
30th percentile: 1.9752927780151368
40th percentile: 2.0854933738708494
50th percentile: 2.1956939697265625
60th percentile: 2.368026542663574
70th percentile: 2.540359115600586
80th percentile: 6.127946424484255
90th percentile: 13.130788469314577
95th percentile: 16.632209491729732
99th percentile: 19.433346309661864
mean time: 5.7543768882751465
%s, retrying in %s seconds...
Received healthy response to inference request in 2.1217126846313477s
Received healthy response to inference request in 2.2115559577941895s
Received healthy response to inference request in 2.2486493587493896s
Received healthy response to inference request in 1.8884892463684082s
Received healthy response to inference request in 2.127047538757324s
5 requests
0 failed requests
5th percentile: 1.935133934020996
10th percentile: 1.981778621673584
20th percentile: 2.0750679969787598
30th percentile: 2.122779655456543
40th percentile: 2.1249135971069335
50th percentile: 2.127047538757324
60th percentile: 2.1608509063720702
70th percentile: 2.1946542739868162
80th percentile: 2.2189746379852293
90th percentile: 2.2338119983673095
95th percentile: 2.24123067855835
99th percentile: 2.2471656227111816
mean time: 2.119490957260132
Pipeline stage StressChecker completed in 42.13s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 1.16s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.71s
Shutdown handler de-registered
chaiml-mistral-fulldata_16288_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-fulldata-16288-v1-profiler
Waiting for inference service chaiml-mistral-fulldata-16288-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4943.76s
Shutdown handler de-registered
chaiml-mistral-fulldata_16288_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-fulldata_16288_v1 status is now torndown due to DeploymentManager action